CN109729273A - Image-pickup method, system, device, computer equipment and storage medium - Google Patents
Image-pickup method, system, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN109729273A CN109729273A CN201910052151.4A CN201910052151A CN109729273A CN 109729273 A CN109729273 A CN 109729273A CN 201910052151 A CN201910052151 A CN 201910052151A CN 109729273 A CN109729273 A CN 109729273A
- Authority
- CN
- China
- Prior art keywords
- image
- target object
- video camera
- frame image
- sequential frame
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Landscapes
- Image Analysis (AREA)
Abstract
This application involves a kind of image-pickup method, system, device, computer equipment and storage mediums.The described method includes: obtaining the sequential frame image of the first video camera acquisition, control signal is generated according to the position of target object in sequential frame image, according to the reflecting mirror rotation in control signal control reflection mirror array, so that target object is present in the acquisition visual field of the second video camera by the mirror-reflection of reflection mirror array, and by the image of the second video camera acquisition target object, wherein, the clarity of the second video camera acquisition image is higher than the clarity of the first video camera acquisition image.Since control signal is generated according to the position of target object, the rotation angle of reflecting mirror can be determined by the position of target object, so that target object is present in the acquisition visual field of the second video camera, the quality of the image of video camera acquisition can be improved.
Description
Technical field
This application involves field of computer technology, more particularly to a kind of image-pickup method, system, device, computer
Equipment and storage medium.
Background technique
With the development of computer technology, image acquisition technology is also evolving.Robot navigation, video monitoring,
In the fields such as sports event live broadcast, need to track moving object and acquire include moving object image.To high speed
Moving object carries out Image Acquisition and often requires to use high-speed camera, in order to analyze motion profile, the posture of moving object
Shape or the rotation of itself, generally require to collect that image quality is more preferable, can differentiate the image of moving object local detail.Due to exploitation
The video camera for being provided simultaneously with high frame per second and high pixel performance is relatively difficult, fuzzy in order to reduce image motion, can be by appropriate
Frame per second is reduced, while shortening time for exposure progress Image Acquisition, but after frame per second reduction, the interval time for obtaining image is elongated, damage
The sampling to the motion feature of moving object has been lost, the image analysis in later period is unfavorable for.
In traditional image acquisition technology, when the object of Image Acquisition quickly moves, acquired image is past
It is bad toward quality.
Summary of the invention
Based on this, it is necessary in view of the above technical problems, provide a kind of image-pickup method, system, device, computer and set
The quality of the image of acquisition can be improved in standby and storage medium.
A kind of image-pickup method, which comprises
Obtain the sequential frame image of the first video camera acquisition；
Control signal is generated according to the position of target object in the sequential frame image；
According to the reflecting mirror rotation in the control signal control reflection mirror array, so that the target object passes through reflection
The mirror-reflection of lens array is present in the acquisition visual field of the second video camera, and acquires the object by second video camera
The image of body；
Wherein, the clarity of the second video camera acquisition image is higher than the clear of first video camera acquisition image
Degree.
The position according to target object in the sequential frame image generates control letter in one of the embodiments,
Number, comprising:
Two-dimensional coordinate of the target object in the sequential frame image is obtained respectively；
The three-dimensional coordinate of the target object is calculated according to the two-dimensional coordinate；
Voltage value is calculated according to the three-dimensional coordinate；
Generate control signal corresponding with the voltage value.
In one of the embodiments, the method also includes:
Image procossing is carried out to the sequential frame image respectively, obtains target sequential frame image；
The image coordinate system pre-established is obtained, described image coordinate system is the seat of the not image comprising the target object
Mark system；
According to described image coordinate system and the target sequential frame image, obtains the target object and connect in the target
Coordinate in continuous frame image.
The reflecting mirror according in the control signal control reflection mirror array rotates in one of the embodiments,
Include:
Obtain voltage value corresponding with the control signal；
According to the corresponding relationship of pre-set voltage value and rotation angle, the corresponding rotation angle of the voltage value is searched
Degree；
According to the reflecting mirror rotation in the rotation angle control reflection mirror array.
In one of the embodiments, the described method includes:
Obtain the number of image frames of the sequential frame image；
When described image frame number is greater than frame number threshold value, the fortune of target object described in the sequential frame image is obtained respectively
Dynamic path；
The track of the target object is analyzed according to the motion path, and obtains analysis result；
The control signal is adjusted according to the analysis result.
The movement road for obtaining target object described in the sequential frame image respectively in one of the embodiments,
Diameter, comprising:
Obtain pre-set target area and candidate region；
The first probability that target object described in the sequential frame image falls into the target area is obtained respectively, is obtained respectively
Target object described in the consecutive image is taken to fall into the second probability of the candidate region；
According to first probability and second probability, mean-shift vector is obtained；
The motion path of the target object is obtained according to the mean-shift vector.
A kind of image capturing system, the system comprises the first video camera, electronic equipment, reflection mirror array and second to take the photograph
Camera, first video camera are connect with the electronic equipment, and the electronic equipment is connect with the reflection mirror array, in which:
The sequential frame image for acquiring sequential frame image, and is sent to the electronics and set by first video camera
It is standby；
The electronic equipment, for obtaining the sequential frame image of the first video camera acquisition, according to the successive frame figure
The position of target object generates control signal as in, and is revolved according to the reflecting mirror in the control signal control reflection mirror array
Turn；
The reflection mirror array, for being reflected according to the control signal rotation, so that the target object passes through reflection
The mirror-reflection of lens array is present in the acquisition visual field of the second video camera；
Second video camera, for acquiring the image of the target object.
A kind of image collecting device, described device include:
Image collection module, for obtaining the sequential frame image of the first video camera acquisition；
Signal generation module generates control signal for the position according to target object in the sequential frame image；
Control module is rotated, for rotating according to the reflecting mirror in the control signal control reflection mirror array, so that institute
It states target object to be present in the acquisition visual field of the second video camera by the mirror-reflection of reflection mirror array, and is taken the photograph by described second
Camera acquires the image of the target object；
Wherein, the clarity of the second video camera acquisition image is higher than the clear of first video camera acquisition image
Degree.
A kind of computer equipment, including memory and processor, the memory are stored with computer program, the processing
Device performs the steps of when executing the computer program
Obtain the sequential frame image of the first video camera acquisition；
Control signal is generated according to the position of target object in the sequential frame image；
According to the reflecting mirror rotation in the control signal control reflection mirror array, so that the target object passes through reflection
The mirror-reflection of lens array is present in the acquisition visual field of the second video camera, and acquires the object by second video camera
The image of body；
Wherein, the clarity of the second video camera acquisition image is higher than the clear of first video camera acquisition image
Degree.
A kind of computer readable storage medium, is stored thereon with computer program, and the computer program is held by processor
It is performed the steps of when row
Obtain the sequential frame image of the first video camera acquisition；
Control signal is generated according to the position of target object in the sequential frame image；
According to the reflecting mirror rotation in the control signal control reflection mirror array, so that the target object passes through reflection
The mirror-reflection of lens array is present in the acquisition visual field of the second video camera, and acquires the object by second video camera
The image of body；
Wherein, the clarity of the second video camera acquisition image is higher than the clear of first video camera acquisition image
Degree.
Above-mentioned image-pickup method, system, device, computer equipment and storage medium are adopted by obtaining the first video camera
The sequential frame image of collection generates control signal according to the position of target object in sequential frame image, anti-according to control signal control
The reflecting mirror rotation in lens array is penetrated, so that target object is present in the second video camera by the mirror-reflection of reflection mirror array
It acquires in the visual field, and by the image of the second video camera acquisition target object, wherein the clarity that the second video camera acquires image is high
In the clarity of the first video camera acquisition image.Since control signal is generated according to the position of target object, reflecting mirror
Rotation angle can be determined by the position of target object, so that target object is present in the acquisition visual field of the second video camera
In, the quality of the image of video camera acquisition can be improved.
Detailed description of the invention
Fig. 1 is the applied environment figure of image-pickup method in one embodiment；
Fig. 2 is the flow diagram of image-pickup method in one embodiment；
Fig. 3 is the flow diagram that the reflecting mirror rotation in reflection mirror array is controlled in one embodiment；
Fig. 4 is the structural block diagram of image collecting device in one embodiment；
Fig. 5 is the internal structure chart of computer equipment in one embodiment.
Specific embodiment
It is with reference to the accompanying drawings and embodiments, right in order to which the objects, technical solutions and advantages of the application are more clearly understood
The application is further elaborated.It should be appreciated that specific embodiment described herein is only used to explain the application, not
For limiting the application.
It is appreciated that term " first " used in this application, " second " etc. can be used to describe various elements herein,
But these elements should not be limited by these terms.These terms are only used to distinguish an element and another element.For example,
In the case where not departing from scope of the present application, the first video camera can be known as the second video camera, and similarly, it can be by second
Video camera is known as the first video camera.First video camera and the second video camera both video camera, but it is not same video camera.
Image-pickup method provided by the embodiments of the present application can be applied in application environment as shown in Figure 1.Such as Fig. 1
Shown, which includes computer equipment 110, the first video camera 120, reflection mirror array 130 and the second video camera
140.Wherein, computer equipment 110 is connect with the first video camera 120, and computer equipment 110 is also connect with reflection mirror array 130,
Reflection mirror array 130 is connect with the second video camera 140.First video camera 120 can acquire sequential frame image, the first video camera
The sequential frame image of acquisition can be transferred to computer equipment 110 by 120.Computer equipment 110 can be according to sequential frame image
The position of middle target object 150 generates control signal, and computer equipment 110 can control reflection mirror array according to control signal
Reflecting mirror rotation in 130, so that target object 150 is present in the second video camera by the mirror-reflection of reflection mirror array 130
In the 140 acquisition visual field.Second video camera 140 can acquire the image of target object 150.Wherein, the second video camera 140 acquires
The clarity of image is higher than the clarity of the first video camera 120 acquisition image.It should be understood that computer equipment 110 can with but
It is not limited to various personal computers, laptop, smart phone, tablet computer and portable wearable device, first takes the photograph
Camera 120 can be high-speed camera, and the second video camera 140 can be high-definition camera.
In one embodiment, as shown in Fig. 2, providing a kind of image-pickup method, it is applied in Fig. 1 in this way
Application environment is illustrated, comprising the following steps:
Step 202, the sequential frame image of the first video camera acquisition is obtained.
Sequential frame image can be the continuous multiple image of the first video camera acquisition, the successive frame of the first video camera acquisition
Image can form video.Wherein, the first video camera can be used for the frame image that acquisition includes high-speed moving object, and first takes the photograph
Camera can be high-speed camera.The quantity of first video camera can be one, two, can also be other quantity, herein not
It limits.When the quantity of the first video camera is two, two the first video cameras may be constructed binocular vision.Wherein, it first takes the photograph
Camera can be industrial high-speed camera.The frame per second of first video camera acquisition image can be 500fps, 600fps, 750fps
Deng it is not limited here.The visual angle of first video camera can be fixed, and the camera lens of the first video camera can be the mirror of adjustable focus
Head.User can placement location to the first video camera and the acquisition visual field be adjusted.First video camera collects successive frame
After image, computer equipment is available to arrive sequential frame image.
Step 204, control signal is generated according to the position of target object in sequential frame image.
Target object can be what user was selected by the first video camera, and target object can be adopting in the first video camera
Collect the object of visual field medium-high speed sports.For example, target object can be the ball of high-speed motion, the people of high-speed motion, high-speed motion
The objects such as vehicle.The position of target object can be specific location of the target object in each sequential frame image, target object
Position can use coordinate representation, can also indicate in other ways, it is not limited here.With with coordinate representation target object
For position, computer equipment can establish coordinate system according to the acquisition visual field of the first video camera, and the position of target object can be with
It is the coordinate points in the acquisition visual field of the first video camera.
Control signal can be used for controlling the rotation of the reflecting mirror in reflection mirror array.The successive frame that computer equipment is got
It include the target object of high-speed motion in image, since target object is in high-speed motion, computer equipment is got each
The position of target object can be different in frame image.Computer equipment can be according to the position of target image in sequential frame image
Set generation control signal.
Step 206, it is rotated according to the reflecting mirror in control signal control reflection mirror array, so that target object passes through reflection
The mirror-reflection of lens array is present in the acquisition visual field of the second video camera, and by the figure of the second video camera acquisition target object
Picture.
It is can wrap in reflection mirror array containing at least one reflecting mirror, motor and transmission device, in reflection mirror array
Motor can control reflecting mirror rotation.Reflection mirror array can be connected by USB interface, Ethernet interface etc. and computer equipment
It connects.Reflecting mirror in reflection mirror array can be adjusted the acquisition visual field of the second video camera by rotation.Second video camera
It can be used for the sequential frame image that acquisition includes target object, the second video camera can be high-definition camera, and the second camera shooting
The clarity that machine acquires image is higher than the clarity of the first video camera acquisition image.The acquisition visual field of second video camera, which can be, to be fallen
Enter the range of the picture of the image of the second video camera acquisition.Wherein, the quantity of the second video camera can be one, two, may be used also
To be other quantity, it is not limited here.Second video camera can carry out Image Acquisition using long focal length lens.Second video camera
It can be work high-definition camera.
Computer equipment can revolve after generating control signal according to the reflecting mirror in control signal control reflection mirror array
Turn.It is generated since control signal is computer equipment according to the position of target object, computer equipment passes through control letter
Number come control the reflecting mirror in reflection mirror array rotation when, can be corresponding with the position of target object.In reflection mirror array
After reflecting mirror rotation, target object can be present in the acquisition visual field of the second video camera by the mirror-reflection of reflection mirror array
In, that is, pass through the acquisition visual field of adjustable second video camera of reflecting mirror in rotating mirror array.Second video camera can be with
Acquisition includes the image of target object.
In the present embodiment, the sequential frame image that computer equipment is acquired by obtaining the first video camera, according to successive frame
The position of target object generates control signal in image, is rotated, is made according to the reflecting mirror in control signal control reflection mirror array
It obtains target object to be present in the acquisition visual field of the second video camera by the mirror-reflection of reflection mirror array, and by the second video camera
Acquire the image of target object, wherein the clarity that the second video camera acquires image is higher than the clear of the first video camera acquisition image
Clear degree.Since control signal is generated according to the position of target object, the rotation angle of reflecting mirror can be by target object
Position determines, so that target object is present in the acquisition visual field of the second video camera, video camera acquisition can be improved
The quality of image.
In one embodiment, a kind of image-pickup method provided can also include the process for generating control signal, tool
Body includes: to obtain two-dimensional coordinate of the target object in sequential frame image respectively；Target object is calculated according to two-dimensional coordinate
Three-dimensional coordinate；Voltage value is calculated according to three-dimensional coordinate；Generate control signal corresponding with voltage value.
The image for the first video camera acquisition that computer equipment is got is sequential frame image, company of the target object in acquisition
Position in continuous frame image is different.Computer equipment can obtain two of target object in sequential frame image respectively
Tie up coordinate, that is, the first video camera can acquire in real time include high-speed motion target object, computer equipment can be according to the
The sequential frame image of one video camera acquisition obtains the two-dimensional coordinate of target object in every frame image.Specifically, computer equipment can
Two-dimensional coordinate of the target object in every frame image is calculated by track algorithm and motion prediction algorithm.
Two-dimensional coordinate of the target object that computer equipment can will acquire in sequential frame image substitutes into affine transformation
In formula, and target object is calculated by affine transformation formula and acquires the three-dimensional coordinate in the visual field in the second video camera.Its
In, affine transformation refers to that a vector space carries out once linear transformation and connects a translation, is transformed to another vector sky
Between.That is, computer equipment can be by affine transformation formula, according to the target object in the frame image of the first video camera acquisition
Three-dimensional coordinate of the target object in the second camera shooting acquisition visual field is calculated in two-dimensional coordinate.
Computer equipment can be according to two-dimensional coordinate and object of the target object in the first video camera acquisition visual field
Three-dimensional coordinate of the body in the second video camera acquisition visual field, calculates corresponding voltage value.Computer equipment can be according to voltage
Value generates corresponding control signal, wherein the control signal that computer equipment generates is digital signal, and computer equipment can will
The control signal of digital signal type is converted into the control signal of analog signal types.
In the present embodiment, computer equipment passes through obtains two-dimensional coordinate of the target object in sequential frame image respectively,
The three-dimensional coordinate that target object is calculated according to two-dimensional coordinate calculates voltage value according to three-dimensional coordinate, generates and voltage value pair
The control signal answered.Computer equipment calculates voltage value according to the coordinate of target object, so that the voltage value and mesh that calculate
The position for marking object is corresponding, and computer equipment generates control signal corresponding with voltage value, and computer equipment control can be improved
The angle and direction of reflecting mirror rotation in reflection mirror array processed.
In one embodiment, a kind of image-pickup method provided can also include the mistake for obtaining the coordinate of target object
Journey, detailed process include: to carry out image procossing to sequential frame image respectively, obtain target sequential frame image；Acquisition pre-establishes
Image coordinate system, image coordinate system be not comprising target object image coordinate system；According to image coordinate system and target
Sequential frame image obtains coordinate of the target object in target sequential frame image.
The sequential frame image that image procossing is used to acquire the first video camera carries out image preprocessing, specifically, computer
Equipment can respectively pre-process sequential frame image.For example, computer equipment frame image can be converted to HSV (Hue,
Saturation, Value, tone, saturation degree, lightness) color space image, computer equipment can remove frame image
It the processing such as makes an uproar, enhance.After computer equipment carries out image procossing to frame image, target object in frame image can be protruded.It calculates
After machine equipment carries out image procossing to sequential frame image respectively, available target sequential frame image.
Image coordinate system can be the coordinate system of the not image comprising target object.Computer equipment can be built by background
Modulo n arithmetic calculate and update do not include target object image, computer equipment can be according to the figure for not including target object
As establishing coordinate system.Computer equipment can store established coordinate system.When computer equipment carries out figure to sequential frame image
As processing, after obtaining target sequential frame image, computer equipment is available pre-establish do not include target object figure
As coordinate system.
Computer equipment it is continuous in target can to obtain target image according to image coordinate system and target sequential frame image
Coordinate in frame image.Specifically, computer equipment can by obtained target sequential frame image and not include respectively target
The image subtraction modulus of object obtains the movement difference of target object, to obtain target object in target sequential frame image
Coordinate.Computer equipment can obtain the coordinate range of target object according to the differences in motion value of target object respectively.
In the present embodiment, it is continuous to obtain target by carrying out image procossing to sequential frame image respectively for computer equipment
Frame image obtains the image coordinate system pre-established, and image coordinate system is the coordinate system of the not image comprising target object, according to
Image coordinate system and target sequential frame image obtain coordinate of the target object in target sequential frame image.Computer equipment
By carrying out image procossing to the sequential frame image of acquisition, and target is obtained according to image coordinate system and target sequential frame image
The coordinate of object can more accurately obtain coordinate of the target object in sequential frame image.
In one embodiment, as shown in figure 3, a kind of image-pickup method provided can also include control reflecting mirror battle array
The process of reflecting mirror rotation in column, specific steps include:
Step 302, voltage value corresponding with control signal is obtained.
Step 304, according to the corresponding relationship of pre-set voltage value and rotation angle, the corresponding rotation of voltage value is searched
Angle.
Step 306, it is rotated according to the reflecting mirror in rotation angle control reflection mirror array.
It can store the corresponding relationship of control signal and voltage value in computer equipment, for example, when control signal is A control
When signal processed, corresponding voltage value can be 3V；When controlling signal is that B controls signal, corresponding voltage value can be 4V.Meter
After calculating machine equipment generation control signal, available voltage value corresponding with control signal.It can store in computer equipment
The corresponding relationship of voltage value and rotation angle, can also be stored with the corresponding relationship of voltage value and direction of rotation.For example, working as voltage
When value is 3V, corresponding rotation angle can be 30 °, and corresponding direction of rotation, which can be, to be rotated to the right.Wherein, computer equipment
The voltage value of middle storage and the corresponding relationship of rotation angle can be what user was arranged by computer equipment.
The voltage value of the available storage of computer equipment and the corresponding relationship of rotation angle, computer equipment can basis
Corresponding relationship searches rotation angle corresponding with voltage value.Computer equipment can be according in rotation angle control reflection mirror array
Reflecting mirror rotation.For example, the voltage value that computer equipment is got is 3V, the voltage value that computer equipment is found is 3V pairs
The rotation angle answered is 30 °, and the voltage value that computer equipment is found is that the corresponding direction of rotation 3V is to rotate to the right, computer
Equipment can control the reflecting mirror in reflection mirror array and rotate to the right 30 °.
In the present embodiment, computer equipment is by obtaining voltage value corresponding with control signal, according to pre-set
The corresponding relationship of voltage value and rotation angle searches the corresponding rotation angle of voltage value, controls reflecting mirror battle array according to rotation angle
Reflecting mirror rotation in column.Since control signal is the Coordinate generation according to target object in sequential frame image, according to control
The corresponding voltage value of signal processed searches rotation angle, and rotates according to the reflecting mirror in rotation angle control reflection mirror array, makes
The angle for obtaining the reflecting mirror rotation in reflection mirror array is more accurate, the mirror-reflection for passing through reflection mirror array convenient for target object
It is present in the acquisition visual field of the second video camera, target object can be made in the center in the second video camera acquisition visual field, improved
The quality of the image of acquisition.
In one embodiment, a kind of image-pickup method provided can also include the process of adjustment control signal, tool
Body process includes: to obtain the number of image frames of sequential frame image；When number of image frames is greater than frame number threshold value, successive frame figure is obtained respectively
The motion path of target object as in；The track of target object is analyzed according to motion path, and obtains analysis result；According to analysis
As a result adjustment control signal.
Number of image frames can be used to indicate that the quantity of the frame image of the first video camera acquisition, computer equipment can be according to adopting
The sequential frame image got is numbered in the collection time.For example, computer equipment can be by first picture number of acquisition
It is the second frame by second picture number of acquisition for first frame.Frame number threshold value can be user and is arranged by computer equipment
, it can also be the specific value that computer equipment generates at random.For example, frame number threshold value can be 5 frames, 7 frames, 10 frames etc.
Specific frame number.
Computer equipment is after getting sequential frame image, the number of image frames of available sequential frame image.Computer is set
The standby number of image frames that can be will acquire is compared with frame number threshold value, and obtains comparison result.When the ratio that computer equipment obtains
When relatively result is that number of image frames is greater than frame number threshold value, computer equipment can obtain the fortune of target object in sequential frame image respectively
Dynamic path.For example, the frame number threshold value stored in computer equipment is 5 frames, the figure for the sequential frame image that computer equipment is got
Picture frame number is 6 frames, and computer equipment can obtain the motion path of target object from this continuous 6 frame image.Specifically, meter
The motion path of target object in sequential frame image can be obtained according to track algorithm and motion prediction algorithm by calculating machine equipment.
Computer equipment can analyze the track of target object according to the motion path of the target object of acquisition, and computer is set
It is standby the stress condition of target object to be analyzed according to the motion path of acquisition, to obtain analysis result.Wherein, analysis knot
It may include the prediction to target object movement in fruit, for example, computer equipment is analyzed by the motion path of target object
It is parabolic path to the track of target object, computer equipment can be according to the parabolic path of target object to target object
Motion path predicted.
Computer equipment can based on the analysis results be adjusted control signal.Since different control signals can be right
Answer different voltage values, different voltage values can correspond to different rotation angle or direction of rotation, and computer equipment can be with
By adjusting control signal, rotation angle or the direction of rotation of the reflecting mirror in reflection mirror array are further adjusted, so that mesh
Mark object is present in the acquisition visual field of the second video camera by the mirror-reflection of the reflection mirror array obtained after rotation.
In the present embodiment, computer equipment passes through the number of image frames for obtaining sequential frame image, when number of image frames is greater than frame
When number threshold value, the motion path of target object in sequential frame image is obtained respectively, and the rail of target object is analyzed according to motion path
Mark, and analyzed as a result, adjustment controls signal based on the analysis results.Computer equipment passes through the motion path to target object
The track for analyzing target object, can adjust control signal based on the analysis results, so that target object after rotation by obtaining
The mirror-reflection of reflection mirror array is present in the acquisition visual field of the second video camera, further increases the figure of the second video camera acquisition
The quality of picture.
In one embodiment, a kind of image-pickup method provided can also include the motion path for obtaining target object
Process, detailed process includes: to obtain pre-set target area and candidate region；Mesh in sequential frame image is obtained respectively
Mark object falls into the first probability of target area, obtains target object in consecutive image respectively and falls into the second general of candidate region
Rate；According to the first probability and the second probability, mean-shift vector is obtained；The fortune of target object is obtained according to mean-shift vector
Dynamic path.
It is pre-set by computer equipment that target area and candidate region can be user, wherein target object goes out
The probability of present target area is greater than the probability that target object appears in candidate region.Mean shift is a nonparametric feature sky
Between analytical technology, be the method for seeking density function extreme point an of iteration, can be used to find the maximum of points of density function.
Mean-shift vector can be used to indicate that the mean vector of offset.First probability can be used to indicate that object in current frame image
Body appears in the probability of target area, and the second probability can be used to indicate that target object appears in candidate region in current frame image
Interior probability.
Computer equipment can calculate in sequential frame image that target object falls into the first of target area in first frame image
Probability, and object module is obtained according to the first probability that target object falls into target area.It should be understood that computer equipment can
To calculate, target object falls into the second probability of candidate region in first frame image in sequential frame image, and is fallen according to target object
The second probability for entering target area obtains candidate family.
Similarity between the available object module of computer equipment and candidate family, and according to the maximum time of similarity
Modeling type obtains current mean-shift vector.Computer equipment can calculate in sequential frame image target object in the second frame image
It falls into the first probability of target area, and calculates in sequential frame image that target object falls into candidate region in the second frame image
Second probability, and the second mean-shift vector is obtained, computer equipment can obtain multiple according to the sequential frame image got
Mean-shift vector.Computer equipment can obtain the motion path of target object according to obtained multiple mean-shift vectors.
Computer equipment can predict the position of target object according to the motion path of obtained target object.
Computer equipment can generate control signal according to the position for the target object that prediction obtains, and then anti-by control signal control
Penetrate the reflecting mirror rotation in lens array.Computer equipment is predicted by the position to target object, so that reflection mirror array
In reflecting mirror rotate in advance, the accuracy rate to the Image Acquisition of target object can be improved.
In the present embodiment, computer equipment is obtained respectively by obtaining pre-set target area and candidate region
It takes target object in sequential frame image to fall into the first probability of target area, obtains target object in consecutive image respectively and fall into time
Second probability of favored area obtains mean-shift vector, is obtained according to mean-shift vector according to the first probability and the second probability
Take the motion path of target object.Mean-shift vector is obtained by calculation in computer equipment, and is obtained according to mean-shift vector
The motion path of target object is taken, the motion path of the target object obtained can be made more accurate.
In one embodiment, a kind of image-pickup method provided can also include the figure of the target object of storage acquisition
The process of picture.The image of target object can be sent to computer after collecting the image of target object by the second video camera
Equipment is stored by computer equipment.
Second video camera can acquire the sequential frame image of target object, and the second video camera can connect with computer equipment
It connects.The image of collected target object can be sent to computer equipment by the second video camera, and computer equipment can store
The image of target object.
In the present embodiment, the second video camera, can be by the image of target object after collecting the image of target object
It is sent to computer equipment, is stored by computer equipment.When needing the image to target object to analyze, computer
Equipment can show the image of target object, analyze convenient for the image to target object.
It should be understood that although each step in above-mentioned each flow chart is successively shown according to the instruction of arrow,
It is these steps is not that the inevitable sequence according to arrow instruction successively executes.Unless expressly stating otherwise herein, these steps
There is no stringent sequences to limit for rapid execution, these steps can execute in other order.Moreover, above-mentioned each flow chart
In at least part step may include that perhaps these sub-steps of multiple stages or stage are not necessarily multiple sub-steps
Completion is executed in synchronization, but can be executed at different times, the execution in these sub-steps or stage sequence is not yet
Necessarily successively carry out, but can be at least part of the sub-step or stage of other steps or other steps in turn
Or it alternately executes.
In one embodiment, a kind of image capturing system is provided.System includes the first video camera, electronic equipment, anti-
Lens array and the second video camera are penetrated, the first video camera is connect with electronic equipment, and electronic equipment is connect with reflection mirror array,
In:
First video camera is sent to electronic equipment for acquiring sequential frame image, and by sequential frame image；
Electronic equipment, for obtaining the sequential frame image of the first video camera acquisition, according to target object in sequential frame image
Position generate control signal, and according to control signal control reflection mirror array in reflecting mirror rotate；
Reflection mirror array, for being reflected according to control signal rotation, so that the mirror surface that target object passes through reflection mirror array
Reflection is present in the acquisition visual field of the second video camera；
Second video camera, for acquiring the image of target object.
In one embodiment, as shown in figure 4, providing a kind of image collecting device, comprising: image collection module 410,
Signal generation module 420 and rotation control module 430, in which:
Image collection module 410, for obtaining the sequential frame image of the first video camera acquisition；
Signal generation module 420 generates control signal for the position according to target object in sequential frame image；
Control module 430 is rotated, for rotating according to the reflecting mirror in control signal control reflection mirror array, so that target
Object is present in the acquisition visual field of the second video camera by the mirror-reflection of reflection mirror array, and acquires mesh by the second video camera
Mark the image of object；Wherein, the clarity of the second video camera acquisition image is higher than the clarity of the first video camera acquisition image.
In one embodiment, signal generation module 420 can be also used for obtaining target object respectively in sequential frame image
In two-dimensional coordinate；The three-dimensional coordinate of target object is calculated according to two-dimensional coordinate；Voltage value is calculated according to three-dimensional coordinate；It is raw
At control signal corresponding with voltage value.
In one embodiment, signal generation module 420 can be also used for carrying out image procossing to sequential frame image respectively,
Obtain target sequential frame image；The image coordinate system pre-established is obtained, image coordinate system is the image for not including target object
Coordinate system；According to image coordinate system and target sequential frame image, seat of the target object in target sequential frame image is obtained
Mark.
In one embodiment, rotation control module 430 can be also used for obtaining voltage value corresponding with control signal；Root
According to the corresponding relationship of pre-set voltage value and rotation angle, the corresponding rotation angle of voltage value is searched；According to rotation angle
Control the reflecting mirror rotation in reflection mirror array.
In one embodiment, signal generation module 420 can be also used for obtaining the number of image frames of sequential frame image；Work as figure
When being greater than frame number threshold value as frame number, the motion path of target object in sequential frame image is obtained respectively；It is analyzed according to motion path
The track of target object, and obtain analysis result；Adjustment control signal based on the analysis results.
In one embodiment, signal generation module 420 can be also used for obtaining pre-set target area and time
Favored area；The first probability that target object in sequential frame image falls into target area is obtained respectively, is obtained in consecutive image respectively
Target object falls into the second probability of candidate region；According to the first probability and the second probability, mean-shift vector is obtained；According to
The motion path of mean-shift vector acquisition target object.
Specific about image collecting device limits the restriction that may refer to above for image-pickup method, herein not
It repeats again.Modules in above-mentioned image collecting device can be realized fully or partially through software, hardware and combinations thereof.On
Stating each module can be embedded in the form of hardware or independently of in the processor in computer equipment, can also store in a software form
In memory in computer equipment, the corresponding operation of the above modules is executed in order to which processor calls.
In one embodiment, a kind of computer equipment is provided, which can be terminal, internal structure
Figure can be as shown in Figure 5.The computer equipment includes processor, the memory, network interface, display connected by system bus
Screen and input unit.Wherein, the processor of the computer equipment is for providing calculating and control ability.The computer equipment is deposited
Reservoir includes non-volatile memory medium, built-in storage.The non-volatile memory medium is stored with operating system and computer journey
Sequence.The built-in storage provides environment for the operation of operating system and computer program in non-volatile memory medium.The calculating
The network interface of machine equipment is used to communicate with external terminal by network connection.When the computer program is executed by processor with
Realize a kind of image-pickup method.The display screen of the computer equipment can be liquid crystal display or electric ink display screen,
The input unit of the computer equipment can be the touch layer covered on display screen, be also possible to be arranged on computer equipment shell
Key, trace ball or Trackpad, can also be external keyboard, Trackpad or mouse etc..
It will be understood by those skilled in the art that structure shown in Fig. 5, only part relevant to application scheme is tied
The block diagram of structure does not constitute the restriction for the computer equipment being applied thereon to application scheme, specific computer equipment
It may include perhaps combining certain components or with different component layouts than more or fewer components as shown in the figure.
In one embodiment, a kind of computer equipment, including memory and processor are provided, is stored in memory
Computer program, the processor perform the steps of when executing computer program
Obtain the sequential frame image of the first video camera acquisition；
Control signal is generated according to the position of target object in sequential frame image；
According to the reflecting mirror rotation in control signal control reflection mirror array, so that target object passes through reflection mirror array
Mirror-reflection is present in the acquisition visual field of the second video camera, and by the image of the second video camera acquisition target object；Wherein,
The clarity that two video cameras acquire image is higher than the clarity of the first video camera acquisition image.
In one embodiment, it is also performed the steps of when processor executes computer program and obtains target object respectively
Two-dimensional coordinate in sequential frame image；The three-dimensional coordinate of target object is calculated according to two-dimensional coordinate；According to three-dimensional coordinate meter
Calculate voltage value；Generate control signal corresponding with voltage value.
In one embodiment, it also performs the steps of respectively when processor executes computer program to sequential frame image
Image procossing is carried out, target sequential frame image is obtained；The image coordinate system pre-established is obtained, image coordinate system is not comprising mesh
Mark the coordinate system of the image of object；According to image coordinate system and target sequential frame image, it is continuous in target to obtain target object
Coordinate in frame image.
In one embodiment, acquisition and control signal pair are also performed the steps of when processor executes computer program
The voltage value answered；According to the corresponding relationship of pre-set voltage value and rotation angle, the corresponding rotation angle of voltage value is searched；
According to the reflecting mirror rotation in rotation angle control reflection mirror array.
In one embodiment, it is also performed the steps of when processor executes computer program and obtains sequential frame image
Number of image frames；When number of image frames is greater than frame number threshold value, the motion path of target object in sequential frame image is obtained respectively；According to
Motion path analyzes the track of target object, and obtains analysis result；Adjustment control signal based on the analysis results.
In one embodiment, it is also performed the steps of when processor executes computer program and obtains pre-set mesh
Mark region and candidate region；The first probability that target object in sequential frame image falls into target area is obtained respectively, is obtained respectively
Target object in consecutive image is taken to fall into the second probability of candidate region；According to the first probability and the second probability, mean value is obtained
Offset vector；The motion path of target object is obtained according to mean-shift vector.
In one embodiment, a kind of computer readable storage medium is provided, computer program is stored thereon with, is calculated
Machine program performs the steps of when being executed by processor
Obtain the sequential frame image of the first video camera acquisition；
Control signal is generated according to the position of target object in sequential frame image；
According to the reflecting mirror rotation in control signal control reflection mirror array, so that target object passes through reflection mirror array
Mirror-reflection is present in the acquisition visual field of the second video camera, and by the image of the second video camera acquisition target object；Wherein,
The clarity that two video cameras acquire image is higher than the clarity of the first video camera acquisition image.
In one embodiment, it is also performed the steps of when computer program is executed by processor and obtains object respectively
Two-dimensional coordinate of the body in sequential frame image；The three-dimensional coordinate of target object is calculated according to two-dimensional coordinate；According to three-dimensional coordinate
Calculate voltage value；Generate control signal corresponding with voltage value.
In one embodiment, it is also performed the steps of when computer program is executed by processor respectively to successive frame figure
As carrying out image procossing, target sequential frame image is obtained；The image coordinate system pre-established is obtained, image coordinate system is not include
The coordinate system of the image of target object；According to image coordinate system and target sequential frame image, obtains target object and connect in target
Coordinate in continuous frame image.
In one embodiment, acquisition and control signal are also performed the steps of when computer program is executed by processor
Corresponding voltage value；According to the corresponding relationship of pre-set voltage value and rotation angle, the corresponding rotation angle of voltage value is searched
Degree；According to the reflecting mirror rotation in rotation angle control reflection mirror array.
In one embodiment, acquisition sequential frame image is also performed the steps of when computer program is executed by processor
Number of image frames；When number of image frames is greater than frame number threshold value, the motion path of target object in sequential frame image is obtained respectively；Root
According to the track of motion path analysis target object, and obtain analysis result；Adjustment control signal based on the analysis results.
In one embodiment, it is pre-set that acquisition is also performed the steps of when computer program is executed by processor
Target area and candidate region；The first probability that target object in sequential frame image falls into target area is obtained respectively, respectively
Obtain the second probability that target object in consecutive image falls into candidate region；According to the first probability and the second probability, obtain
It is worth offset vector；The motion path of target object is obtained according to mean-shift vector.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, the computer program can be stored in a non-volatile computer
In read/write memory medium, the computer program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein,
To any reference of memory, storage, database or other media used in each embodiment provided herein,
Including non-volatile and/or volatile memory.Nonvolatile memory may include read-only memory (ROM), programming ROM
(PROM), electrically programmable ROM (EPROM), electrically erasable ROM (EEPROM) or flash memory.Volatile memory may include
Random access memory (RAM) or external cache.By way of illustration and not limitation, RAM is available in many forms,
Such as static state RAM (SRAM), dynamic ram (DRAM), synchronous dram (SDRAM), double data rate sdram (DDRSDRAM), enhancing
Type SDRAM (ESDRAM), synchronization link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM
(RDRAM), direct memory bus dynamic ram (DRDRAM) and memory bus dynamic ram (RDRAM) etc..
Each technical characteristic of above embodiments can be combined arbitrarily, for simplicity of description, not to above-described embodiment
In each technical characteristic it is all possible combination be all described, as long as however, the combination of these technical characteristics be not present lance
Shield all should be considered as described in this specification.
The several embodiments of the application above described embodiment only expresses, the description thereof is more specific and detailed, but simultaneously
It cannot therefore be construed as limiting the scope of the patent.It should be pointed out that coming for those of ordinary skill in the art
It says, without departing from the concept of this application, various modifications and improvements can be made, these belong to the protection of the application
Range.Therefore, the scope of protection shall be subject to the appended claims for the application patent.
Claims (10)
1. a kind of image-pickup method, which comprises
Obtain the sequential frame image of the first video camera acquisition；
Control signal is generated according to the position of target object in the sequential frame image；
According to the reflecting mirror rotation in the control signal control reflection mirror array, so that the target object passes through reflecting mirror battle array
The mirror-reflection of column is present in the acquisition visual field of the second video camera, and acquires the target object by second video camera
Image；
Wherein, the clarity of the second video camera acquisition image is higher than the clarity of first video camera acquisition image.
2. the method according to claim 1, wherein the position according to target object in the sequential frame image
Set generation control signal, comprising:
Two-dimensional coordinate of the target object in the sequential frame image is obtained respectively；
The three-dimensional coordinate of the target object is calculated according to the two-dimensional coordinate；
Voltage value is calculated according to the three-dimensional coordinate；
Generate control signal corresponding with the voltage value.
3. according to the method described in claim 2, it is characterized in that, the method also includes:
Image procossing is carried out to the sequential frame image respectively, obtains target sequential frame image；
The image coordinate system pre-established is obtained, described image coordinate system is the coordinate of the not image comprising the target object
System；
According to described image coordinate system and the target sequential frame image, the target object is obtained in the target successive frame
Coordinate in image.
4. according to the method described in claim 2, it is characterized in that, described control in reflection mirror array according to the control signal
Reflecting mirror rotation, comprising:
Obtain voltage value corresponding with the control signal；
According to the corresponding relationship of pre-set voltage value and rotation angle, the corresponding rotation angle of the voltage value is searched；
According to the reflecting mirror rotation in the rotation angle control reflection mirror array.
5. the method according to claim 1, wherein the described method includes:
Obtain the number of image frames of the sequential frame image；
When described image frame number is greater than frame number threshold value, the movement road of target object described in the sequential frame image is obtained respectively
Diameter；
The track of the target object is analyzed according to the motion path, and obtains analysis result；
The control signal is adjusted according to the analysis result.
6. according to the method described in claim 5, it is characterized in that, described obtain target described in the sequential frame image respectively
The motion path of object, comprising:
Obtain pre-set target area and candidate region；
The first probability that target object described in the sequential frame image falls into the target area is obtained respectively, obtains institute respectively
State the second probability that target object described in consecutive image falls into the candidate region；
According to first probability and second probability, mean-shift vector is obtained；
The motion path of the target object is obtained according to the mean-shift vector.
7. a kind of image capturing system, which is characterized in that the system comprises the first video camera, electronic equipment, reflection mirror arrays
And second video camera, first video camera are connect with the electronic equipment, the electronic equipment and the reflection mirror array
Connection, in which:
First video camera is sent to the electronic equipment for acquiring sequential frame image, and by the sequential frame image；
The electronic equipment, for obtaining the sequential frame image of the first video camera acquisition, according in the sequential frame image
The position of target object generates control signal, and is rotated according to the reflecting mirror in the control signal control reflection mirror array；
The reflection mirror array, for being reflected according to the control signal rotation, so that the target object passes through reflecting mirror battle array
The mirror-reflection of column is present in the acquisition visual field of the second video camera；
Second video camera, for acquiring the image of the target object.
8. a kind of image collecting device, which is characterized in that described device includes:
Image collection module, for obtaining the sequential frame image of the first video camera acquisition；
Signal generation module generates control signal for the position according to target object in the sequential frame image；
Control module is rotated, for rotating according to the reflecting mirror in the control signal control reflection mirror array, so that the mesh
Mark object is present in the acquisition visual field of the second video camera by the mirror-reflection of reflection mirror array, and by second video camera
Acquire the image of the target object；
Wherein, the clarity of the second video camera acquisition image is higher than the clarity of first video camera acquisition image.
9. a kind of computer equipment, including memory and processor, the memory are stored with computer program, feature exists
In the step of processor realizes any one of claims 1 to 6 the method when executing the computer program.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program
The step of method described in any one of claims 1 to 6 is realized when being executed by processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910052151.4A CN109729273A (en) | 2019-01-21 | 2019-01-21 | Image-pickup method, system, device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910052151.4A CN109729273A (en) | 2019-01-21 | 2019-01-21 | Image-pickup method, system, device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109729273A true CN109729273A (en) | 2019-05-07 |
Family
ID=66298475
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910052151.4A Pending CN109729273A (en) | 2019-01-21 | 2019-01-21 | Image-pickup method, system, device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109729273A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110853416A (en) * | 2019-11-27 | 2020-02-28 | 上海体育学院 | Video feedback training system for motor skill learning |
| CN111369631A (en) * | 2020-03-06 | 2020-07-03 | 厦门华联电子股份有限公司 | Sample image automatic acquisition method and device based on XYZ axis platform |
| CN113179371A (en) * | 2021-04-21 | 2021-07-27 | 新疆爱华盈通信息技术有限公司 | Shooting method, device and snapshot system |
| CN113630543A (en) * | 2020-05-06 | 2021-11-09 | 杭州海康威视数字技术股份有限公司 | Falling object and person smashing event monitoring method and device, electronic equipment and monitoring system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1404682A (en) * | 2000-08-25 | 2003-03-19 | 皇家菲利浦电子有限公司 | Method and apparatus for tracking an object of interest in a digital image |
| JP2014103597A (en) * | 2012-11-21 | 2014-06-05 | Olympus Corp | Imaging apparatus |
| CN105592269A (en) * | 2016-03-03 | 2016-05-18 | 北京志光伯元科技有限公司 | Motion target capturing and tracking device and motion target capturing and tracking method |
| CN107409204A (en) * | 2015-04-01 | 2017-11-28 | 索尼公司 | Power-efficient multicamera system |
| CN108986161A (en) * | 2018-06-19 | 2018-12-11 | 亮风台（上海）信息科技有限公司 | A kind of three dimensional space coordinate estimation method, device, terminal and storage medium |
-
2019
- 2019-01-21 CN CN201910052151.4A patent/CN109729273A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1404682A (en) * | 2000-08-25 | 2003-03-19 | 皇家菲利浦电子有限公司 | Method and apparatus for tracking an object of interest in a digital image |
| JP2014103597A (en) * | 2012-11-21 | 2014-06-05 | Olympus Corp | Imaging apparatus |
| CN107409204A (en) * | 2015-04-01 | 2017-11-28 | 索尼公司 | Power-efficient multicamera system |
| CN105592269A (en) * | 2016-03-03 | 2016-05-18 | 北京志光伯元科技有限公司 | Motion target capturing and tracking device and motion target capturing and tracking method |
| CN108986161A (en) * | 2018-06-19 | 2018-12-11 | 亮风台（上海）信息科技有限公司 | A kind of three dimensional space coordinate estimation method, device, terminal and storage medium |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110853416A (en) * | 2019-11-27 | 2020-02-28 | 上海体育学院 | Video feedback training system for motor skill learning |
| CN111369631A (en) * | 2020-03-06 | 2020-07-03 | 厦门华联电子股份有限公司 | Sample image automatic acquisition method and device based on XYZ axis platform |
| CN111369631B (en) * | 2020-03-06 | 2023-04-07 | 厦门华联电子股份有限公司 | Sample image automatic acquisition method and device based on XYZ axis platform |
| CN113630543A (en) * | 2020-05-06 | 2021-11-09 | 杭州海康威视数字技术股份有限公司 | Falling object and person smashing event monitoring method and device, electronic equipment and monitoring system |
| CN113630543B (en) * | 2020-05-06 | 2022-12-06 | 杭州海康威视数字技术股份有限公司 | Falling object and person smashing event monitoring method and device, electronic equipment and monitoring system |
| CN113179371A (en) * | 2021-04-21 | 2021-07-27 | 新疆爱华盈通信息技术有限公司 | Shooting method, device and snapshot system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109729273A (en) | Image-pickup method, system, device, computer equipment and storage medium | |
| Bhat et al. | Deep burst super-resolution | |
| Zhang et al. | Exploiting temporal consistency for real-time video depth estimation | |
| CN107481270B (en) | Table tennis target tracking and trajectory prediction method, device, storage medium and computer equipment | |
| Chin et al. | Star tracking using an event camera | |
| JP7274048B2 (en) | Motion recognition method, apparatus, computer program and computer device | |
| JP2020042476A5 (en) | ||
| JP4970557B2 (en) | Face search and detection in digital image capture device | |
| Sauer et al. | Tracking holistic object representations | |
| JP2021506017A (en) | Object detector and object detection method | |
| Mustaniemi et al. | Gyroscope-aided motion deblurring with deep networks | |
| CN111160375A (en) | Three-dimensional key point prediction and deep learning model training method, device and equipment | |
| CN111179419A (en) | Three-dimensional key point prediction and deep learning model training method, device and equipment | |
| CN111080776B (en) | Human body action three-dimensional data acquisition and reproduction processing method and system | |
| Kim et al. | Simvodis: Simultaneous visual odometry, object detection, and instance segmentation | |
| WO2021093637A1 (en) | Focusing method and apparatus, electronic device, and computer readable storage medium | |
| CN110992401A (en) | Target tracking method and device, computer equipment and storage medium | |
| CN108876806A (en) | Method for tracking target and system, storage medium and equipment based on big data analysis | |
| CN114937125B (en) | Reconstructable metric information prediction method, reconstructable metric information prediction device, computer equipment and storage medium | |
| US20060215036A1 (en) | Method and apparatus for video stabilization | |
| CN110992393B (en) | Target motion tracking method based on vision | |
| JP7032913B2 (en) | Image processing device, image processing method, computer program | |
| CN113438409B (en) | Delay calibration method, delay calibration device, computer equipment and storage medium | |
| JP2007304721A (en) | Image processing device and image processing method | |
| JP2022101519A (en) | Method of creating hyperspectral high speed camera image using generative adversarial network algorithm |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190507 |
|
| RJ01 | Rejection of invention patent application after publication |